Contact Info
Email: pei-chun.su@yale.edu
Phone: 1+(714) 718-2949
Office: Leet Oliver Memorial Hall 218
Mailing address: 12 Hillhouse Ave, New Haven, CT 06511
Leet Oliver Memorial Hall, Department of Applied and Computational Mathematics,
Yale University
I am a Gibbs Assistant Professor in the Department of Applied and Computational Mathematics at Yale University. As both an applied mathematician and a physician, I am driven by the challenge of extracting meaningful patterns from complex medical data. My research focuses on developing algorithms that uncover the geometric structures underlying such data, enabling efficient matrix factorizations and optimal denoising techniques, with downstream applications in fetal ECG (fECG) signal separation, localized biomarker discovery, and scientific machine learning.
Education
I received my Ph.D. in Mathematics from Duke University. Prior to that, I earned an M.S. in Bioengineering from the University of California, Los Angeles, and an M.D. and B.Sc. in Electrical and Computer Engineering from National Taiwan University, where I also completed two years of clinical training as a medical intern at National Taiwan University Hospital.
Research
Preprints and Submitted Manuscripts
"A Fetal ECG Extraction Framework for Morphological Analysis Using Non-Invasive Multi-Channel Abdominal Recordings," with Giulia Baldazzi, Danilo Pani, Hau-Tieng Wu, submitted to Biomedical Signal Processing and Control, 2026.
"Data-Driven Matrix Recovery with High-Dimensional Noise via Optimal Shrinkage of Singular Values and Wavelet Shrinkage of Singular Vectors," Submitted to IEEE Transactions on Information Theory, 2026
"Learning the Analytic Geometry of Transformations to Achieve Efficient Computation," with Ronald R. Coifman, June 2025
"Intrinsic and Extrinsic Organized Attention: Softmax Invariance and Network Sparsity," with Oluwadamilola Fasina, Ruben V.C. Pohle, Ronald R. Coifman, June 2025
Published and Accepted Journal Articles
"Sympathetic nerve activity recovery from the skin recording using the modern optimal shrinkage technique," with Chao-Yi Chen, Chia-Hao Kuo, Wei-Chung Tsai, Hau-Tieng Wu, Biomedical Signal Processing and Control, Volume 119 , June 2026
"DiCoLo: Integration-free and cluster-free detection of localized differential gene co-expression in single-cell data," with Ruiqi Li, Junchen Yang , Ariel Jaffe, Ofir Lindenbaum, Yuval Kluger, Accepted by Annual International Conference on Research in Computational Molecular Biology, 2026
"From clutter to clarity: Emergent neural operators via questionnaire metrics," with Anastasia S. Georgiou, Arjun Manoj, Ronald R. Coifman, Ioannis G. Kevrekidis, Somdatta Goswami, Computers & Chemical Engineering, Volume 201, October 2025
"Data-driven optimal shrinkage of singular values under high-dimensional noise with separable covariance structure with application," with Hau-Tieng Wu, Applied and Computational Harmonic Analysis, Volume 74, January 2025
"Optimal recovery of precision matrix for Mahalanobis distance from high-dimensional noisy observations in manifold learning," with Matan Gavish, Ronen Talmon, Hau-Tieng Wu, Information and Inference: A Journal of the IMA, Volume 11, Issue 4, December 2022, Pages 1173–1202
"Robust T-End Detection via T-End Signal Quality Index and Optimal Shrinkage," with Elsayed Z Soliman and Hau-Tieng Wu, Sensors (Basel), December 2020
"Fetal heart rate variability responsiveness to maternal stress, non-invasively detected from maternal transabdominal ECG," with Silvia M Lobmaier, A Müller, C Zelgert, C Shen, G Schmidt, B Haller, G Berg, B Fabre, J Weyrich, H-T Wu, M G Frasch, M C Antonelli, Archives of Gynecology and Obstetrics, February 2020
"Recovery of the fetal electrocardiogram for morphological analysis from two trans-abdominal channels via optimal shrinkage," with Stephen Miller, Salim Idriss, Piers Barker, Hau-Tieng Wu, Physiological Measurement, December 2019
Books and Dissertation
"Modern Signal Processing Tools for Fetal Electrocardiogram Extraction from Single-Channel Transabdominal Maternal Electrocardiogram," with Hau-Tieng Wu, Innovative Technologies and Signal Processing in Perinatal Medicine, pp 149–169, April 2023
"Denoise high dimensional dataset with complicated noise and its clinical applications," Dissertation, Duke University, 2023